TemporAI: v0.0.3

Release Notes

Changes:

• Improved modularity.
• There may be breaking API changes, see documentation for v0.0.3.

Other:

• Improved documentation.
• Improved tests (reorganized, coverage increased).
• Some bug fixes and refactoring.

TemporAI v0.0.2

Release Notes

Additions:

• AutoML in the form of hyperparameter tuning and pipeline search.
• A data loader for UCI Diabetes dataset.

Changes:

• Imputation methods reorganized: static_tabular_imputer and ts_tabular_imputer replace static_imputation.

Other:

• Improved documentation.
• Improved tests (reorganized, coverage increased).
• Some bug fixes and refactoring.

TemporAI v0.0.1: First alpha release

Release Notes

The following methods are included in this release:

---

Prediction

One-off

Prediction where targets are static.

• Classification (category: prediction.one_off.classification)

Name	Description	Reference
nn_classifier	Neural-net based classifier. Supports multiple recurrent models, like RNN, LSTM, Transformer etc.	---
ode_classifier	Classifier based on ordinary differential equation (ODE) solvers.	---
cde_classifier	Classifier based Neural Controlled Differential Equations for Irregular Time Series.	Paper
laplace_ode_classifier	Classifier based Inverse Laplace Transform (ILT) algorithms implemented in PyTorch.	Paper

• Regression (category: prediction.one_off.regression)

Name	Description	Reference
nn_regressor	Neural-net based regressor. Supports multiple recurrent models, like RNN, LSTM, Transformer etc.	---
ode_regressor	Regressor based on ordinary differential equation (ODE) solvers.	---
cde_regressor	Regressor based Neural Controlled Differential Equations for Irregular Time Series.	Paper
laplace_ode_regressor	Regressor based Inverse Laplace Transform (ILT) algorithms implemented in PyTorch.	Paper

Temporal

Prediction where targets are temporal (time series).

• Classification (category: prediction.temporal.classification)

Name	Description	Reference
seq2seq_classifier	Seq2Seq prediction, classification	---

• Regression (category: prediction.temporal.regression)

Name	Description	Reference
seq2seq_regressor	Seq2Seq prediction, regression	---

Time-to-Event

Risk estimation given event data (category: time_to_event)

Name	Description	Reference
dynamic_deephit	Dynamic-DeepHit incorporates the available longitudinal data comprising various repeated measurements (rather than only the last available measurements) in order to issue dynamically updated survival predictions	Paper
ts_coxph	Create embeddings from the time series and use a CoxPH model for predicting the survival function	---
ts_xgb	Create embeddings from the time series and use a SurvivalXGBoost model for predicting the survival function	---

Treatment effects

One-off

Treatment effects estimation where treatments are a one-off event.

• Regression on the outcomes (category: treatments.one_off.regression)

Name	Description	Reference
synctwin_regressor	SyncTwin is a treatment effect estimation method tailored for observational studies with longitudinal data, applied to the LIP setting: Longitudinal, Irregular and Point treatment.	Paper

Temporal

Treatment effects estimation where treatments are temporal (time series).

• Classification on the outcomes (category: treatments.temporal.classification)

Name	Description	Reference
crn_classifier	The Counterfactual Recurrent Network (CRN), a sequence-to-sequence model that leverages the available patient observational data to estimate treatment effects over time.	Paper

• Regression on the outcomes (category: treatments.temporal.regression)

Name	Description	Reference
crn_regressor	The Counterfactual Recurrent Network (CRN), a sequence-to-sequence model that leverages the available patient observational data to estimate treatment effects over time.	Paper

Preprocessing

Imputation

• Static data (category: preprocessing.imputation.static)

Name	Description	Reference
static_imputation	Use HyperImpute to impute both the static and temporal data	Paper

• Temporal data (category: preprocessing.imputation.temporal)

Name	Description	Reference
ffill	Propagate last valid observation forward to next valid	---
bfill	Use next valid observation to fill gap	---

Scaling

• Static data (category: preprocessing.scaling.static)

Name	Description	Reference
static_standard_scaler	Scale the static features using a StandardScaler	---
static_minmax_scaler	Scale the static features using a MinMaxScaler	---

• Temporal data (category: preprocessing.scaling.temporal)

Name	Description	Reference
ts_standard_scaler	Scale the temporal features using a StandardScaler	---
ts_minmax_scaler	Scale the temporal features using a MinMaxScaler	---

---

Additional features:

• Pipelines: tempor.plugins.pipeline.
• Benchmarking: tempor.benchmarks (one off classification, regression, time-to-event).

TemporAI v0.0.1.dev0: First dev release

Release Notes

Initial dev release, not for production use.